Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
mikf
GitHub Repository: mikf/gallery-dl
 Path: blob/master/gallery_dl/extractor/architizer.py
5399 views
1
# -*- coding: utf-8 -*-

2


3
# Copyright 2021-2025 Mike Fährmann

4
#

5
# This program is free software; you can redistribute it and/or modify

6
# it under the terms of the GNU General Public License version 2 as

7
# published by the Free Software Foundation.

8


9
"""Extractors for https://architizer.com/"""

10


11
from .common import GalleryExtractor, Extractor, Message

12
from .. import text

13


14


15
class ArchitizerProjectExtractor(GalleryExtractor):

16
    """Extractor for project pages on architizer.com"""

17
    category = "architizer"

18
    subcategory = "project"

19
    root = "https://architizer.com"

20
    directory_fmt = ("{category}", "{firm}", "{title}")

21
    filename_fmt = "{filename}.{extension}"

22
    archive_fmt = "{gid}_{num}"

23
    pattern = r"(?:https?://)?architizer\.com/projects/([^/?#]+)"

24
    example = "https://architizer.com/projects/NAME/"

25


26
    def __init__(self, match):

27
        url = f"{self.root}/projects/{match[1]}/"

28
        GalleryExtractor.__init__(self, match, url)

29


30
    def metadata(self, page):

31
        extr = text.extract_from(page)

32
        extr('id="Pages"', "")

33


34
        return {

35
            "title"      : extr("data-name='", "'"),

36
            "slug"       : extr("data-slug='", "'"),

37
            "gid"        : extr("data-gid='", "'").rpartition(".")[2],

38
            "firm"       : extr("data-firm-leaders-str='", "'"),

39
            "location"   : extr("<h2>", "<").strip(),

40
            "type"       : text.unescape(text.remove_html(extr(

41
                '<div class="title">Type</div>', '<br'))),

42
            "status"     : text.remove_html(extr(

43
                '<div class="title">STATUS</div>', '</')),

44
            "year"       : text.remove_html(extr(

45
                '<div class="title">YEAR</div>', '</')),

46
            "size"       : text.remove_html(extr(

47
                '<div class="title">SIZE</div>', '</')),

48
            "description": text.unescape(extr(

49
                '<span class="copy js-copy">', '</span></div>')

50
                .replace("<br />", "\n")),

51
        }

52


53
    def images(self, page):

54
        return [

55
            (url, None)

56
            for url in text.extract_iter(

57
                page, 'property="og:image:secure_url" content="', "?")

58
        ]

59


60


61
class ArchitizerFirmExtractor(Extractor):

62
    """Extractor for all projects of a firm"""

63
    category = "architizer"

64
    subcategory = "firm"

65
    root = "https://architizer.com"

66
    pattern = r"(?:https?://)?architizer\.com/firms/([^/?#]+)"

67
    example = "https://architizer.com/firms/NAME/"

68


69
    def __init__(self, match):

70
        Extractor.__init__(self, match)

71
        self.firm = match[1]

72


73
    def items(self):

74
        url = url = f"{self.root}/firms/{self.firm}/?requesting_merlin=pages"

75
        page = self.request(url).text

76
        data = {"_extractor": ArchitizerProjectExtractor}

77


78
        for project in text.extract_iter(page, '<a href="/projects/', '"'):

79
            if not project.startswith("q/"):

80
                url = f"{self.root}/projects/{project}"

81
                yield Message.Queue, url, data

82


83